agentleFS
ai-search-guruai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool/skills/listings/SKILL.md

listings

Skill432 starsChanged 12 days agoMITView on GitHub

Lists the sources AI cites in a market and whether they list you.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read its page to see whether it lists the brand.

    line 31
  2. Distinctive:

    Never say a site lists the brand, or doesn't, without reading its page.

    line 42
  3. Distinctive:

    Don't invent contacts, names or addresses for outreach.

    line 43
  4. Distinctive:

    Never promise a listing will bring citations.

    line 44

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Listing gaps

The directories, marketplaces, review sites and publishers AI engines cite in the brand's category, and whether each one lists the brand.

When to use

  • "Which directories and review sites does AI trust in our category?", "Where are we missing?", "Publisher sites."
  • To fix what AI gets wrong about the brand, the Fix wrong claims about us skill fits better.

What to read

  1. list_citations with the external filter: the third-party sites AI cites for the brand's prompts, and how often.
  2. list_ai_answers for the prompts that cite them: which brands those answers recommend.
  3. list_competitors: the competitors to look for on each site.
  4. fetch_page for each site's page about the category: whether it names the brand.

Steps

  1. Take the market the person names; with none, every market the brand tracks.
  2. List the third-party sources AI cites most, by kind: directory, marketplace, review site, publisher.
  3. For each: the answers that cite it, and the competitors it names.
  4. Read its page to see whether it lists the brand. When the page can't be read, write "unknown".
  5. Suggest a next step for each: ask for a listing, update a profile, or nothing to do.

Output

  1. A table: Source, Kind, Answers citing it, Lists you, Competitors listed, Next step.
  2. Outreach drafts for the top three, when the person asks.
  3. Sending leaves the workspace: the person does it. Chat sends nothing.

Don't

  • Never say a site lists the brand, or doesn't, without reading its page.
  • Don't invent contacts, names or addresses for outreach.
  • Never promise a listing will bring citations.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.